Michael R. Lucas

Mayo Clinic · United States

Unclaimed · AI-structured profileOpenAlex

Mayo Clinic researcher applying pathology foundation models to whole-slide image analysis and diagnostic workflows

papers here

reviewed by Evolve

first-author

corresponding

—

works · OpenAlex

h-index · OpenAlex

Bibliometric figures come from OpenAlex (2026-10-17) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.

Research profile

Output—

Output is not scored yet: the snapshot lists h-index 0, i10-index 0, and only 2 indexed works (2026), so total publication volume and peer-reviewed output cannot be measured until the OpenAlex record is more complete.

Impact—

Impact cannot be scored from this snapshot: h-index and i10-index are both 0 and no citation counts are attached to the two preprints, so this axis would measure citations, citation-normalized influence, and uptake once data accumulates.

Focus100/100

Focus scores 100, the strongest signal in this profile. The OpenAlex field distribution lists computational pathology as the sole field, and all four indexed topics — AI in cancer detection (2), radiomics and machine learning in medical imaging (2), artificial intelligence in healthcare and education (1), and digital imaging for blood diseases (1) — sit on pathology imaging and AI. Both reviewed 2026 preprints are computational pathology papers.

Collaboration66/100

Collaboration scores 66, based on 26 distinct coauthors in the indexed record. The 12 recurring names — including Ayushi Sinha, Shashank Yadav, Benjamin Holmes, Pravat Das, Santiago Romero-Brufau, James S. Lewis, Scott H. Kaufmann, and Saghir Alfasly — point to a stable Mayo Clinic-centered author group. Across the two reviewed papers Lucas moves from a middle-author slot on WILSON to last author on the triage study, consistent with a growing role inside a team science setting.

Activity32/100

Activity scores 32, the weakest of the scored dimensions. The raw record shows 2 works in the last three years, with countsByYear listing only 2026 (2 works); no earlier publication years appear in this snapshot. Both entries are arXiv preprints rather than journal articles, so the profile reflects a very recent and still thin publication record.

Reproducibility20/100

Reproducibility scores 20 (reproMean 20), computed from 1 repro-scored paper in the reviewed catalog, and both reviewed papers carry a low reproducibility readiness rating. Evolve's reviews cite the same limitations repeatedly: zero-shot evaluation, single-institution or private Mayo cohort data, no baselines, no tests, and no public data release for the slide-triage study. These ratings describe current artifacts, not the researcher's methods.

Research summary

Michael R. Lucas is a researcher at Mayo Clinic (US) whose indexed work sits almost entirely in computational pathology, the sole field in the OpenAlex distribution behind a focus score of 100. The reviewed catalog contains two 2026 arXiv preprints. The first, WILSON — a pathology foundation model framework for patient-level analysis and diagnostic text generation, lists Lucas as a middle author; Evolve's review notes that multi-magnification composite images let the framework match models 9.4× larger at roughly 1000× less compute, while flagging zero-shot evaluation and single-institution data. The second, on morphology signals in whole slide image foundation models for automatic slide triage, lists Lucas as last author (not corresponding); it reports promising zero-shot triage on two private Mayo cohorts, with no baselines, tests, or public data, yielding low reproducibility readiness for both papers. Radar dimensions reflect this early profile: collaboration 66, supported by 26 distinct coauthors and a recurring Mayo-based author group; activity 32, from 2 works in the last three years with 2 indexed in 2026; reproducibility 20 (reproMean 20 across 1 repro-scored paper). Output and impact are unscored because the snapshot reports h-index and i10-index of 0 and no verified publication counts. This is a name-resolved, early-stage profile built from OpenAlex bibliometrics and Evolve's paper reviews only.

Collaboration pattern

Lucas's indexed record involves 26 distinct coauthors (collaboration score 66), with a recurring core including Ayushi Sinha, Shashank Yadav, Benjamin Holmes, Pravat Das, Aaron W. Bogan, James S. Lewis, Santiago Romero-Brufau, and Saghir Alfasly — a pattern consistent with a stable Mayo Clinic-based research group. Positioning shifts between the two 2026 preprints, from middle author on WILSON to last author on the slide-triage study (non-corresponding), suggesting an evolving role within a collaborative computational pathology team.

Research keywords

whole slide imagespathology foundation modelscomputational pathologyzero-shot classificationslide triageCONCHdiagnostic text generationmulti-magnification composite imagesradiomicsAI in cancer detection

Highlights

WILSON pathology foundation model framework: large-model accuracy at a fraction of the compute
As a middle author on this 2026 arXiv framework paper, Lucas contributes to a pathology foundation model system for patient-level analysis and diagnostic text generation; Evolve's verdict reports that multi-magnification composite images match models 9.4× larger at ~1000× less compute, while flagging zero-shot evaluation and single-institution data.
Zero-shot slide triage using morphology signals in whole slide image foundation models
Lucas is last author (not corresponding) on this 2026 study, which automatically triages whole slide images using pathology foundation models such as CONCH; Evolve finds the zero-shot results promising on two private Mayo cohorts but notes no baselines, no tests, and no public data, yielding low reproducibility readiness.

Timeline

2026Co-authored (middle position) the WILSON framework preprint on arXiv, a pathology foundation model for patient-level analysis and diagnostic text generation.
2026Last-authored (non-corresponding) the arXiv study showing that morphology signals in whole slide image foundation models can automatically triage slides.
2026OpenAlex countsByYear records 2 indexed works in 2026, the only publication year in this snapshot, matching 2 works over the last three years.

Papers in the Evolve catalog

Frequent co-authors

Ayushi Sinha×1 Shashank Yadav×1 Benjamin Holmes×1 Pravat Das×1 Aaron W. Bogan×1 James S. Lewis×1 Santiago Romero-Brufau×1 Andrew Y. K. Foong×1 Scott H. Kaufmann×1 Kathryn M. Van Abel×1 David M. Routman×1 Saghir Alfasly×1

About this profile

This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.

Bibliometrics come from an OpenAlex snapshot (identity: openalex) with no ORCID linkage, so this profile is name-resolved from public bibliographic data and disambiguation is not guaranteed.
h-index and i10-index are 0 in the snapshot, reflecting absent citation data rather than verified citation performance.
Only two 2026 arXiv preprints are reviewed here; no peer-reviewed journal publications, funding, or award data are included in the input.
Reproducibility rests on a single repro-scored paper (reproPapers: 1) and both reviewed papers are rated low readiness, so the score of 20 carries wide uncertainty.